Compare commits

..
33 changed files with 175 additions and 875 deletions
-12
View File
@@ -2048,18 +2048,6 @@ password. All of these options come from their similarly-named [Django settings]
Defaults to None.
#### [`PAPERLESS_REMOTE_OCR_MODE=<str>`](#PAPERLESS_REMOTE_OCR_MODE) {#PAPERLESS_REMOTE_OCR_MODE}
: Which documents are sent to the remote OCR engine.
- `always`: every document of a supported file type is sent to the remote
engine, bypassing the local OCR engine.
- `workflow_only`: documents are processed locally unless a workflow
explicitly enables remote OCR for them, letting you use the remote engine
selectively.
Defaults to "always".
## AI {#ai}
#### [`PAPERLESS_AI_ENABLED=<bool>`](#PAPERLESS_AI_ENABLED) {#PAPERLESS_AI_ENABLED}
-14
View File
@@ -456,20 +456,6 @@ def score(
return 10
```
**Remote services**
If your parser sends document content to a remote service, declare it:
```python
class MyCustomParser:
uses_remote_service = True
```
Paperless-ngx excludes such parsers when the document being consumed has not
been marked for remote processing, so users can keep remote OCR off by default
and enable it selectively with a workflow. Parsers that do not declare the
attribute are treated as fully local and are always considered.
**Archive and rendition flags**
```python
+1 -6
View File
@@ -1086,16 +1086,11 @@ Paperless-ngx supports performing OCR on documents using remote services. At the
[Microsoft's Azure "Document Intelligence" service](https://azure.microsoft.com/en-us/products/ai-services/ai-document-intelligence).
This is of course a paid service (with a free tier) which requires an Azure account and subscription. Azure AI is not affiliated with
Paperless-ngx in any way. When enabled, Paperless-ngx will automatically send appropriate documents to Azure for OCR processing, bypassing
the local OCR engine. See the [configuration](configuration.md#PAPERLESS_REMOTE_OCR_ENGINE) options for more details. These
settings can be supplied as environment variables or via **Application Configuration**.
the local OCR engine. See the [configuration](configuration.md#PAPERLESS_REMOTE_OCR_ENGINE) options for more details.
Additionally, when using a commercial service with this feature, consider both potential costs as well as any associated file size
or page limitations (e.g. with a free tier).
By default, every document of a supported file type is sent to the remote engine. To use it more selectively, set the
[remote OCR mode](configuration.md#PAPERLESS_REMOTE_OCR_MODE) to `workflow_only`. Documents are then processed locally
unless a workflow explicitly enables remote OCR for them, so you can limit the remote engine to particular documents.
## Architecture
Paperless-ngx consists of the following components:
@@ -14,48 +14,43 @@
<a ngbNavLink>{{category}}</a>
<ng-template ngbNavContent>
<div class="p-3">
@for (section of getCategorySections(category); track section) {
@if (section) {
<h5 class="mt-4 mb-3">{{section}}</h5>
}
<div class="row row-cols-1 row-cols-md-2 row-cols-lg-3 g-2">
@for (option of getCategoryOptions(category, section); track option.key) {
<div class="col">
<div class="card bg-light">
<div class="card-body">
<div class="card-title d-flex align-items-center">
<h6 class="mb-0">
{{option.title}}
</h6>
<a class="btn btn-sm btn-link" title="Read the documentation about this setting" i18n-title [href]="getDocsUrl(option.config_key)" target="_blank" referrerpolicy="no-referrer">
<i-bs name="info-circle"></i-bs>
</a>
@if (isSet(option.key)) {
<button type="button" class="btn btn-sm btn-link text-danger ms-auto pe-0" title="Reset" i18n-title (click)="resetOption(option.key)">
<i-bs class="me-1" name="x"></i-bs><ng-container i18n>Reset</ng-container>
</button>
}
</div>
<div class="mb-n3">
@switch (option.type) {
@case (ConfigOptionType.Select) { <pngx-input-select [formControlName]="option.key" [error]="errors[option.key]" [items]="option.choices" [allowNull]="true"></pngx-input-select> }
@case (ConfigOptionType.Number) { <pngx-input-number [formControlName]="option.key" [error]="errors[option.key]" [showAdd]="false"></pngx-input-number> }
@case (ConfigOptionType.Boolean) { <pngx-input-switch [formControlName]="option.key" [error]="errors[option.key]" [showUnsetNote]="true" [horizontal]="true" title="Enable" i18n-title></pngx-input-switch> }
@case (ConfigOptionType.String) { <pngx-input-text [formControlName]="option.key" [error]="errors[option.key]"></pngx-input-text> }
@case (ConfigOptionType.JSON) { <pngx-input-text [formControlName]="option.key" [error]="errors[option.key]"></pngx-input-text> }
@case (ConfigOptionType.File) { <pngx-input-file [formControlName]="option.key" (upload)="uploadFile($event, option.key)" [error]="errors[option.key]"></pngx-input-file> }
@case (ConfigOptionType.Password) { <pngx-input-password [formControlName]="option.key" [error]="errors[option.key]"></pngx-input-password> }
}
</div>
@if (option.note) {
<div class="form-text fst-italic">{{option.note}}</div>
<div class="row row-cols-1 row-cols-md-2 row-cols-lg-3 g-2">
@for (option of getCategoryOptions(category); track option.key) {
<div class="col">
<div class="card bg-light">
<div class="card-body">
<div class="card-title d-flex align-items-center">
<h6 class="mb-0">
{{option.title}}
</h6>
<a class="btn btn-sm btn-link" title="Read the documentation about this setting" i18n-title [href]="getDocsUrl(option.config_key)" target="_blank" referrerpolicy="no-referrer">
<i-bs name="info-circle"></i-bs>
</a>
@if (isSet(option.key)) {
<button type="button" class="btn btn-sm btn-link text-danger ms-auto pe-0" title="Reset" i18n-title (click)="resetOption(option.key)">
<i-bs class="me-1" name="x"></i-bs><ng-container i18n>Reset</ng-container>
</button>
}
</div>
<div class="mb-n3">
@switch (option.type) {
@case (ConfigOptionType.Select) { <pngx-input-select [formControlName]="option.key" [error]="errors[option.key]" [items]="option.choices" [allowNull]="true"></pngx-input-select> }
@case (ConfigOptionType.Number) { <pngx-input-number [formControlName]="option.key" [error]="errors[option.key]" [showAdd]="false"></pngx-input-number> }
@case (ConfigOptionType.Boolean) { <pngx-input-switch [formControlName]="option.key" [error]="errors[option.key]" [showUnsetNote]="true" [horizontal]="true" title="Enable" i18n-title></pngx-input-switch> }
@case (ConfigOptionType.String) { <pngx-input-text [formControlName]="option.key" [error]="errors[option.key]"></pngx-input-text> }
@case (ConfigOptionType.JSON) { <pngx-input-text [formControlName]="option.key" [error]="errors[option.key]"></pngx-input-text> }
@case (ConfigOptionType.File) { <pngx-input-file [formControlName]="option.key" (upload)="uploadFile($event, option.key)" [error]="errors[option.key]"></pngx-input-file> }
@case (ConfigOptionType.Password) { <pngx-input-password [formControlName]="option.key" [error]="errors[option.key]"></pngx-input-password> }
}
</div>
@if (option.note) {
<div class="form-text fst-italic">{{option.note}}</div>
}
</div>
</div>
}
</div>
}
</div>
}
</div>
</div>
</ng-template>
</li>
@@ -8,11 +8,7 @@ import { NgbModule } from '@ng-bootstrap/ng-bootstrap'
import { NgSelectModule } from '@ng-select/ng-select'
import { NgxBootstrapIconsModule, allIcons } from 'ngx-bootstrap-icons'
import { of, throwError } from 'rxjs'
import {
ConfigCategory,
ConfigSection,
OutputTypeConfig,
} from 'src/app/data/paperless-config'
import { OutputTypeConfig } from 'src/app/data/paperless-config'
import { ConfigService } from 'src/app/services/config.service'
import { SettingsService } from 'src/app/services/settings.service'
import { ToastService } from 'src/app/services/toast.service'
@@ -162,24 +158,4 @@ describe('ConfigComponent', () => {
component.resetOption('barcodes_enabled')
expect(component.configForm.get('barcodes_enabled').value).toBeNull()
})
it('should group options into sections within a category, or not', () => {
const sections = component.getCategorySections(ConfigCategory.OCR)
expect(sections).toEqual([null, ConfigSection.RemoteOCR])
expect(
component
.getCategoryOptions(ConfigCategory.OCR)
.map((option) => option.key)
).toContain('output_type')
expect(
component
.getCategoryOptions(ConfigCategory.OCR, ConfigSection.RemoteOCR)
.map((option) => option.key)
).toEqual([
'remote_ocr_engine',
'remote_ocr_api_key',
'remote_ocr_endpoint',
'remote_ocr_mode',
])
})
})
@@ -74,20 +74,8 @@ export class ConfigComponent
return Object.values(ConfigCategory)
}
getCategorySections(category: string): string[] {
return [
...new Set(
PaperlessConfigOptions.filter((o) => o.category === category).map(
(o) => o.section ?? null // null means no section
)
),
]
}
getCategoryOptions(category: string, section: string = null): ConfigOption[] {
return PaperlessConfigOptions.filter(
(o) => o.category === category && (o.section ?? null) === section
)
getCategoryOptions(category: string): ConfigOption[] {
return PaperlessConfigOptions.filter((o) => o.category === category)
}
initialConfig: PaperlessConfig
@@ -17,10 +17,6 @@ const permissions = [
'view_document',
'change_document',
'delete_document',
'add_sharelinkbundle',
'view_sharelinkbundle',
'change_sharelinkbundle',
'delete_sharelinkbundle',
'change_tag',
'view_documenttype',
]
@@ -79,7 +75,6 @@ describe('PermissionsSelectComponent', () => {
component.ngOnInit()
component.writeValue(permissions)
expect(component.typesWithAllActions).toContain('Document')
expect(component.typesWithAllActions).toContain('ShareLinkBundle')
})
it('should update checkboxes on permissions set', () => {
@@ -90,10 +85,6 @@ describe('PermissionsSelectComponent', () => {
expect(input1.nativeElement.checked).toBeTruthy()
const input2 = fixture.debugElement.query(By.css('input#Tag_Change'))
expect(input2.nativeElement.checked).toBeTruthy()
const bundleInput = fixture.debugElement.query(
By.css('input#ShareLinkBundle_Add')
)
expect(bundleInput.nativeElement.checked).toBeTruthy()
})
it('disable checkboxes when permissions are inherited', () => {
-55
View File
@@ -54,10 +54,6 @@ export const ConfigCategory = {
AI: $localize`AI Settings`,
}
export const ConfigSection = {
RemoteOCR: $localize`Remote OCR`,
}
export const LLMEmbeddingBackendConfig = {
OPENAI_LIKE: 'openai-like',
HUGGINGFACE: 'huggingface',
@@ -69,15 +65,6 @@ export const LLMBackendConfig = {
OLLAMA: 'ollama',
}
export const RemoteOCREngineConfig = {
AZURE_AI: 'azureai',
}
export const RemoteOCRModeConfig = {
ALWAYS: 'always',
WORKFLOW_ONLY: 'workflow_only',
}
export interface ConfigOption {
key: string
title: string
@@ -85,7 +72,6 @@ export interface ConfigOption {
choices?: Array<{ id: string; name: string }>
config_key?: string
category: string
section?: string
note?: string
}
@@ -195,43 +181,6 @@ export const PaperlessConfigOptions: ConfigOption[] = [
config_key: 'PAPERLESS_OCR_USER_ARGS',
category: ConfigCategory.OCR,
},
{
key: 'remote_ocr_engine',
title: $localize`Remote OCR Engine`,
type: ConfigOptionType.Select,
choices: mapToItems(RemoteOCREngineConfig),
config_key: 'PAPERLESS_REMOTE_OCR_ENGINE',
category: ConfigCategory.OCR,
section: ConfigSection.RemoteOCR,
note: $localize`Enabling remote OCR sends documents to a third-party service for processing. Consider the privacy implications as well as potential costs before enabling.`,
},
{
key: 'remote_ocr_api_key',
title: $localize`Remote OCR API Key`,
type: ConfigOptionType.Password,
config_key: 'PAPERLESS_REMOTE_OCR_API_KEY',
category: ConfigCategory.OCR,
section: ConfigSection.RemoteOCR,
},
{
key: 'remote_ocr_endpoint',
title: $localize`Remote OCR Endpoint`,
type: ConfigOptionType.String,
config_key: 'PAPERLESS_REMOTE_OCR_ENDPOINT',
category: ConfigCategory.OCR,
section: ConfigSection.RemoteOCR,
note: $localize`Required when using the Azure AI engine.`,
},
{
key: 'remote_ocr_mode',
title: $localize`Remote OCR Mode`,
type: ConfigOptionType.Select,
choices: mapToItems(RemoteOCRModeConfig),
config_key: 'PAPERLESS_REMOTE_OCR_MODE',
category: ConfigCategory.OCR,
section: ConfigSection.RemoteOCR,
note: $localize`Which documents are sent to the remote engine. Use 'workflow_only' to keep remote OCR off unless a workflow enables it for a document.`,
},
{
key: 'app_logo',
title: $localize`Application Logo`,
@@ -449,10 +398,6 @@ export interface PaperlessConfig extends ObjectWithId {
barcode_enable_tag: boolean
barcode_tag_mapping: object
barcode_tag_split: boolean
remote_ocr_engine: string
remote_ocr_api_key: string
remote_ocr_endpoint: string
remote_ocr_mode: string
ai_enabled: boolean
llm_embedding_backend: string
llm_embedding_model: string
@@ -120,12 +120,6 @@ describe('PermissionsService', () => {
actionKey: 'View', // PermissionAction.View
typeKey: 'SystemMonitoring', // PermissionType.SystemMonitoring
})
expect(permissionsService.getPermissionKeys('add_sharelinkbundle')).toEqual(
{
actionKey: 'Add', // PermissionAction.Add
typeKey: 'ShareLinkBundle', // PermissionType.ShareLinkBundle
}
)
})
it('correctly checks explicit global permissions', () => {
@@ -275,10 +269,6 @@ describe('PermissionsService', () => {
'view_sharelink',
'change_sharelink',
'delete_sharelink',
'add_sharelinkbundle',
'view_sharelinkbundle',
'change_sharelinkbundle',
'delete_sharelinkbundle',
'add_workflow',
'view_workflow',
'change_workflow',
@@ -26,7 +26,6 @@ export enum PermissionType {
User = '%s_user',
Group = '%s_group',
ShareLink = '%s_sharelink',
ShareLinkBundle = '%s_sharelinkbundle',
CustomField = '%s_customfield',
Workflow = '%s_workflow',
ProcessedMail = '%s_processedmail',
-8
View File
@@ -53,7 +53,6 @@ from documents.utils import copy_basic_file_stats
from documents.utils import copy_file_with_basic_stats
from documents.utils import run_subprocess
from paperless.config import OcrConfig
from paperless.config import RemoteOCRConfig
from paperless.models import ArchiveFileGenerationChoices
from paperless.parsers import ParserContext
from paperless.parsers import ParserProtocol
@@ -452,19 +451,12 @@ class ConsumerPlugin(
except Exception as e:
self.log.error(f"Error attempting to clean PDF: {e}")
# Workflows have already run at this point, so the metadata knows
# whether this document was singled out for remote OCR
allow_remote = (
self.metadata.remote_ocr or RemoteOCRConfig().remote_ocr_by_default
)
# Based on the mime type, get the parser for that type
parser_class: type[ParserProtocol] | None = (
get_parser_registry().get_parser_for_file(
mime_type,
self.filename,
self.working_copy,
allow_remote=allow_remote,
)
)
if not parser_class:
-3
View File
@@ -34,7 +34,6 @@ class DocumentMetadataOverrides:
skip_asn_if_exists: bool = False
version_label: str | None = None
actor_id: int | None = None
remote_ocr: bool = False
def update(self, other: "DocumentMetadataOverrides") -> "DocumentMetadataOverrides":
"""
@@ -58,8 +57,6 @@ class DocumentMetadataOverrides:
self.actor_id = other.actor_id
if other.skip_asn_if_exists:
self.skip_asn_if_exists = True
if other.remote_ocr:
self.remote_ocr = True
if other.version_label is not None:
self.version_label = other.version_label
+1 -10
View File
@@ -66,7 +66,6 @@ from documents.utils import compute_checksum
from documents.utils import identity
from documents.workflows.utils import get_workflows_for_trigger
from paperless.config import AIConfig
from paperless.config import RemoteOCRConfig
from paperless.logging import consume_task_id
from paperless.parsers import ParserContext
from paperless.parsers.registry import get_parser_registry
@@ -338,17 +337,10 @@ def bulk_update_documents(document_ids) -> None:
@shared_task
def update_document_content_maybe_archive_file(
document_id,
*,
remote_ocr: bool = False,
) -> None:
def update_document_content_maybe_archive_file(document_id) -> None:
"""
Re-creates OCR content and thumbnail for a document, and archive file if
it exists.
Remote OCR is used only when the engine is configured to handle everything
or if explicitly asked for via ``remote_ocr``.
"""
document = Document.objects.get(id=document_id)
@@ -358,7 +350,6 @@ def update_document_content_maybe_archive_file(
mime_type,
document.original_filename or "",
document.source_path,
allow_remote=remote_ocr or RemoteOCRConfig().remote_ocr_by_default,
)
if not parser_class:
@@ -72,10 +72,6 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
"barcode_enable_tag": None,
"barcode_tag_mapping": None,
"barcode_tag_split": None,
"remote_ocr_engine": None,
"remote_ocr_api_key": None,
"remote_ocr_endpoint": None,
"remote_ocr_mode": None,
"ai_enabled": False,
"llm_embedding_backend": None,
"llm_embedding_model": None,
@@ -874,49 +870,6 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
config.refresh_from_db()
self.assertEqual(config.llm_api_key, None)
def test_update_remote_ocr_api_key(self) -> None:
"""
GIVEN:
- Existing config with remote_ocr_api_key specified
WHEN:
- API to update remote_ocr_api_key is called with all *s
- API to update remote_ocr_api_key is called with empty string
THEN:
- remote_ocr_api_key is unchanged
- remote_ocr_api_key is set to None
"""
config = ApplicationConfiguration.objects.first()
assert config is not None
config.remote_ocr_api_key = "1234567890"
config.save()
# Test with all *
response = self.client.patch(
f"{self.ENDPOINT}1/",
json.dumps(
{
"remote_ocr_api_key": "*" * 32,
},
),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_200_OK)
config.refresh_from_db()
self.assertEqual(config.remote_ocr_api_key, "1234567890")
# Test with empty string
response = self.client.patch(
f"{self.ENDPOINT}1/",
json.dumps(
{
"remote_ocr_api_key": "",
},
),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_200_OK)
config.refresh_from_db()
self.assertEqual(config.remote_ocr_api_key, None)
def test_enable_ai_index_triggers_update(self) -> None:
"""
GIVEN:
-80
View File
@@ -1559,72 +1559,6 @@ class PostConsumeTestCase(DirectoriesMixin, GetConsumerMixin, TestCase):
consumer.run_post_consume_script(doc)
class TestConsumerRemoteOCR(
DirectoriesMixin,
FileSystemAssertsMixin,
GetConsumerMixin,
TestCase,
):
"""
The consumer resolves the remote OCR mode and the per-document request from
workflows into the allow_remote flag it hands to the parser registry.
"""
def setUp(self) -> None:
super().setUp()
patcher = mock.patch("documents.consumer.get_parser_registry")
self.mock_registry = patcher.start()
self.mock_registry.return_value.get_parser_for_file.return_value = DummyParser
self.addCleanup(patcher.stop)
def _consume(self, *, overrides: DocumentMetadataOverrides | None = None) -> bool:
src = (
Path(__file__).parent
/ "samples"
/ "documents"
/ "originals"
/ "0000001.pdf"
)
dst = self.dirs.scratch_dir / "sample.pdf"
shutil.copy(src, dst)
with self.get_consumer(dst, overrides=overrides) as consumer:
consumer.run()
_, kwargs = self.mock_registry.return_value.get_parser_for_file.call_args
return kwargs["allow_remote"]
@override_settings(REMOTE_OCR_MODE="always")
def test_always_mode_allows_remote(self) -> None:
"""
GIVEN: Remote OCR mode is 'always'.
WHEN: A document is consumed without any workflow asking for it.
THEN: The registry is allowed to pick the remote parser.
"""
self.assertTrue(self._consume())
@override_settings(REMOTE_OCR_MODE="workflow_only")
def test_workflow_only_mode_denies_remote_by_default(self) -> None:
"""
GIVEN: Remote OCR mode is 'workflow_only'.
WHEN: A document is consumed and nothing asked for remote OCR.
THEN: The remote parser is excluded.
"""
self.assertFalse(self._consume())
@override_settings(REMOTE_OCR_MODE="workflow_only")
def test_workflow_only_mode_allows_remote_when_requested(self) -> None:
"""
GIVEN: Remote OCR mode is 'workflow_only'.
WHEN: A workflow set remote_ocr on the metadata overrides.
THEN: The registry is allowed to pick the remote parser.
"""
self.assertTrue(
self._consume(overrides=DocumentMetadataOverrides(remote_ocr=True)),
)
class TestMetadataOverrides(TestCase):
def test_update_skip_asn_if_exists(self) -> None:
base = DocumentMetadataOverrides()
@@ -1632,20 +1566,6 @@ class TestMetadataOverrides(TestCase):
base.update(incoming)
self.assertTrue(base.skip_asn_if_exists)
def test_update_remote_ocr(self) -> None:
base = DocumentMetadataOverrides()
base.update(DocumentMetadataOverrides(remote_ocr=True))
self.assertTrue(base.remote_ocr)
def test_update_remote_ocr_is_not_unset(self) -> None:
"""
A later workflow that says nothing must not undo an earlier one that
asked for remote OCR.
"""
base = DocumentMetadataOverrides(remote_ocr=True)
base.update(DocumentMetadataOverrides())
self.assertTrue(base.remote_ocr)
def test_update_actor_and_version_label(self) -> None:
base = DocumentMetadataOverrides(
actor_id=1,
-39
View File
@@ -287,45 +287,6 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
self.assertNotEqual(Document.objects.get(pk=doc.pk).content, "test")
class TestUpdateContentRemoteOCR(DirectoriesMixin, TestCase):
"""
Consumption workflows do not run on reprocess, so the remote parser is
used only in 'always' mode or when the caller explicitly asks for it.
"""
def setUp(self) -> None:
super().setUp()
patcher = mock.patch("documents.tasks.get_parser_registry")
self.mock_registry = patcher.start()
self.mock_registry.return_value.get_parser_for_file.return_value = None
self.addCleanup(patcher.stop)
self.doc = Document.objects.create(
title="test",
content="my document",
checksum="wow",
mime_type="application/pdf",
)
def _allow_remote(self, **kwargs) -> bool:
tasks.update_document_content_maybe_archive_file(self.doc.pk, **kwargs)
_, call_kwargs = self.mock_registry.return_value.get_parser_for_file.call_args
return call_kwargs["allow_remote"]
@override_settings(REMOTE_OCR_MODE="always")
def test_always_mode_allows_remote(self) -> None:
self.assertTrue(self._allow_remote())
@override_settings(REMOTE_OCR_MODE="workflow_only")
def test_workflow_only_mode_denies_remote_by_default(self) -> None:
self.assertFalse(self._allow_remote())
@override_settings(REMOTE_OCR_MODE="workflow_only")
def test_workflow_only_mode_allows_remote_when_requested(self) -> None:
self.assertTrue(self._allow_remote(remote_ocr=True))
class TestAIIndex(DirectoriesMixin, TestCase):
@override_settings(
AI_ENABLED=True,
+5 -8
View File
@@ -338,16 +338,13 @@ def check_deprecated_v2_ocr_env_vars(
@register()
def check_remote_ocr_mode(app_configs: Any, **kwargs: Any) -> list[Error]:
# Import here because checks.py runs before the app registry is ready
from paperless.models import RemoteOCRMode
valid_modes = {mode.value for mode in RemoteOCRMode}
if settings.REMOTE_OCR_MODE not in valid_modes:
def check_remote_parser_configured(app_configs: Any, **kwargs: Any) -> list[Error]:
if settings.REMOTE_OCR_ENGINE == "azureai" and not (
settings.REMOTE_OCR_ENDPOINT and settings.REMOTE_OCR_API_KEY
):
return [
Error(
f"PAPERLESS_REMOTE_OCR_MODE is set to {settings.REMOTE_OCR_MODE!r}, "
f"expected one of {sorted(valid_modes)}.",
"Azure AI remote parser requires endpoint and API key to be configured.",
),
]
-40
View File
@@ -9,7 +9,6 @@ from paperless.models import CleanChoices
from paperless.models import ColorConvertChoices
from paperless.models import ModeChoices
from paperless.models import OutputTypeChoices
from paperless.models import RemoteOCRMode
@dataclasses.dataclass
@@ -186,45 +185,6 @@ class GeneralConfig(BaseConfig):
self.app_logo = app_config.app_logo.url if app_config.app_logo else None
@dataclasses.dataclass
class RemoteOCRConfig(BaseConfig):
"""
Settings for the remote (cloud) OCR parser
"""
remote_ocr_engine: str | None = dataclasses.field(init=False)
remote_ocr_api_key: str | None = dataclasses.field(init=False)
remote_ocr_endpoint: str | None = dataclasses.field(init=False)
remote_ocr_mode: RemoteOCRMode = dataclasses.field(init=False)
def __post_init__(self) -> None:
app_config = self._get_config_instance()
self.remote_ocr_engine = (
app_config.remote_ocr_engine or settings.REMOTE_OCR_ENGINE
)
self.remote_ocr_api_key = (
app_config.remote_ocr_api_key or settings.REMOTE_OCR_API_KEY
)
self.remote_ocr_endpoint = (
app_config.remote_ocr_endpoint or settings.REMOTE_OCR_ENDPOINT
)
self.remote_ocr_mode = app_config.remote_ocr_mode or RemoteOCRMode(
settings.REMOTE_OCR_MODE,
)
@property
def remote_ocr_by_default(self) -> bool:
"""
Whether every supported document goes to the remote engine.
When False the remote engine is used only for documents that
explicitly asked for it, i.e. a workflow matched during consumption or
the user ticked the box when reprocessing.
"""
return self.remote_ocr_mode == RemoteOCRMode.ALWAYS
@dataclasses.dataclass
class AIConfig(BaseConfig):
"""
@@ -1,44 +0,0 @@
# Generated by Django 5.2.16 on 2026-08-10 14:37
from django.db import migrations
from django.db import models
class Migration(migrations.Migration):
dependencies = [
("paperless", "0013_applicationconfiguration_llm_request_timeout"),
]
operations = [
migrations.AddField(
model_name="applicationconfiguration",
name="remote_ocr_api_key",
field=models.CharField(
blank=True,
max_length=1024,
null=True,
verbose_name="Sets the remote OCR API key",
),
),
migrations.AddField(
model_name="applicationconfiguration",
name="remote_ocr_endpoint",
field=models.CharField(
blank=True,
max_length=256,
null=True,
verbose_name="Sets the remote OCR endpoint",
),
),
migrations.AddField(
model_name="applicationconfiguration",
name="remote_ocr_engine",
field=models.CharField(
blank=True,
choices=[("azureai", "Azure AI Document Intelligence")],
max_length=32,
null=True,
verbose_name="Sets the remote OCR engine",
),
),
]
@@ -1,27 +0,0 @@
# Generated by Django 5.2.16 on 2026-08-10 15:43
from django.db import migrations
from django.db import models
class Migration(migrations.Migration):
dependencies = [
("paperless", "0014_applicationconfiguration_remote_ocr_api_key_and_more"),
]
operations = [
migrations.AddField(
model_name="applicationconfiguration",
name="remote_ocr_mode",
field=models.CharField(
blank=True,
choices=[
("always", "All supported documents"),
("workflow_only", "Only when a workflow enables it"),
],
max_length=32,
null=True,
verbose_name="Sets which documents are sent to the remote OCR engine",
),
),
]
-55
View File
@@ -74,23 +74,6 @@ class ColorConvertChoices(models.TextChoices):
CMYK = ("CMYK", _("CMYK"))
class RemoteOCREngine(models.TextChoices):
"""
Matches to PAPERLESS_REMOTE_OCR_ENGINE
"""
AZURE_AI = ("azureai", _("Azure AI Document Intelligence"))
class RemoteOCRMode(models.TextChoices):
"""
Matches to PAPERLESS_REMOTE_OCR_MODE
"""
ALWAYS = ("always", _("All supported documents"))
WORKFLOW_ONLY = ("workflow_only", _("Only when a workflow enables it"))
class LLMEmbeddingBackend(models.TextChoices):
OPENAI_LIKE = ("openai-like", _("OpenAI-compatible"))
HUGGINGFACE = ("huggingface", _("Huggingface"))
@@ -303,44 +286,6 @@ class ApplicationConfiguration(AbstractSingletonModel):
null=True,
)
"""
Settings for the remote OCR parser
"""
# PAPERLESS_REMOTE_OCR_ENGINE
remote_ocr_engine = models.CharField(
verbose_name=_("Sets the remote OCR engine"),
blank=True,
null=True,
max_length=32,
choices=RemoteOCREngine.choices,
)
# PAPERLESS_REMOTE_OCR_API_KEY
remote_ocr_api_key = models.CharField(
verbose_name=_("Sets the remote OCR API key"),
blank=True,
null=True,
max_length=1024,
)
# PAPERLESS_REMOTE_OCR_ENDPOINT
remote_ocr_endpoint = models.CharField(
verbose_name=_("Sets the remote OCR endpoint"),
blank=True,
null=True,
max_length=256,
)
# PAPERLESS_REMOTE_OCR_MODE
remote_ocr_mode = models.CharField(
verbose_name=_("Sets which documents are sent to the remote OCR engine"),
blank=True,
null=True,
max_length=32,
choices=RemoteOCRMode.choices,
)
"""
AI related settings
"""
-9
View File
@@ -134,11 +134,6 @@ class ParserProtocol(Protocol):
Author or organisation name.
url : str
URL for documentation, source code, or issue tracker.
Parsers that send document content to a remote service should additionally
set ``uses_remote_service = True`` so the registry can exclude them when
remote processing has not been requested for a document. The attribute is
optional so a parser that omits it is treated as fully local.
"""
# ------------------------------------------------------------------
@@ -150,10 +145,6 @@ class ParserProtocol(Protocol):
author: str
url: str
# NOTE: uses_remote_service is not declared here, the registry reads it
# with getattr(cls, ..., False) for backwards-compatibility with existing
# parsers
# ------------------------------------------------------------------
# Class methods
# ------------------------------------------------------------------
-14
View File
@@ -334,8 +334,6 @@ class ParserRegistry:
mime_type: str,
filename: str,
path: Path | None = None,
*,
allow_remote: bool = True,
) -> type[ParserProtocol] | None:
"""Return the best parser class for the given file, or None.
@@ -361,11 +359,6 @@ class ParserRegistry:
path:
Optional filesystem path to the file. Forwarded to each
parser's score method.
allow_remote:
When False, parsers that declare ``uses_remote_service = True``
are excluded from consideration, so a document is never sent to
a remote service. Parsers that do not declare the attribute
are treated as local and are always considered.
Returns
-------
@@ -381,13 +374,6 @@ class ParserRegistry:
if mime_type not in parser_class.supported_mime_types():
continue
if not allow_remote and getattr(
parser_class,
"uses_remote_service",
False,
):
continue
score = parser_class.score(mime_type, filename, path)
if score is None:
continue
+10 -19
View File
@@ -61,18 +61,6 @@ class RemoteEngineConfig:
self.api_key = api_key
self.endpoint = endpoint
@classmethod
def from_app_config(cls) -> Self:
"""Build the config from the app config, falling back to the env."""
from paperless.config import RemoteOCRConfig
app_config = RemoteOCRConfig()
return cls(
engine=app_config.remote_ocr_engine,
api_key=app_config.remote_ocr_api_key,
endpoint=app_config.remote_ocr_endpoint,
)
def engine_is_valid(self) -> bool:
"""Return True when the engine is known and fully configured."""
return (
@@ -102,9 +90,6 @@ class RemoteDocumentParser:
Maintainer name.
url : str
Issue tracker / source URL.
uses_remote_service : bool
Content is sent to a remote service, True so that the registry
can skip this parser if remote processing was not requested.
"""
name: str = "Paperless-ngx Remote OCR Parser"
@@ -112,8 +97,6 @@ class RemoteDocumentParser:
author: str = "Paperless-ngx Contributors"
url: str = "https://github.com/paperless-ngx/paperless-ngx"
uses_remote_service: bool = True
# ------------------------------------------------------------------
# Class methods
# ------------------------------------------------------------------
@@ -162,7 +145,11 @@ class RemoteDocumentParser:
20 when the remote engine is configured and the MIME type is
supported, otherwise None.
"""
config = RemoteEngineConfig.from_app_config()
config = RemoteEngineConfig(
engine=settings.REMOTE_OCR_ENGINE,
api_key=settings.REMOTE_OCR_API_KEY,
endpoint=settings.REMOTE_OCR_ENDPOINT,
)
if not config.engine_is_valid():
return None
if mime_type not in _SUPPORTED_MIME_TYPES:
@@ -257,7 +244,11 @@ class RemoteDocumentParser:
Whether an archive copy is wanted. For PDFs, False skips the
remote engine and uses locally-extracted text instead.
"""
config = RemoteEngineConfig.from_app_config()
config = RemoteEngineConfig(
engine=settings.REMOTE_OCR_ENGINE,
api_key=settings.REMOTE_OCR_API_KEY,
endpoint=settings.REMOTE_OCR_ENDPOINT,
)
if not config.engine_is_valid():
logger.warning(
+5 -14
View File
@@ -219,13 +219,6 @@ class ApplicationConfigurationSerializer(
allow_null=True,
max_length=1024,
)
remote_ocr_api_key = ObfuscatedPasswordField(
required=False,
allow_null=True,
max_length=1024,
)
OBFUSCATED_FIELDS = ("llm_api_key", "remote_ocr_api_key")
def run_validation(self, data):
# Empty strings treated as None to avoid unexpected behavior
@@ -237,13 +230,11 @@ class ApplicationConfigurationSerializer(
data["language"] = None
if "llm_output_language" in data and data["llm_output_language"] == "":
data["llm_output_language"] = None
for field in self.OBFUSCATED_FIELDS:
if field in data and data[field] is not None:
if data[field] == "":
data[field] = None
# Not a real value, don't overwrite the stored one
elif len(data[field].replace("*", "")) == 0:
del data[field]
if "llm_api_key" in data and data["llm_api_key"] is not None:
if data["llm_api_key"] == "":
data["llm_api_key"] = None
elif len(data["llm_api_key"].replace("*", "")) == 0:
del data["llm_api_key"]
return super().run_validation(data)
def update(self, instance, validated_data):
-1
View File
@@ -1197,7 +1197,6 @@ WEBHOOKS_ALLOW_INTERNAL_REQUESTS = get_bool_from_env(
REMOTE_OCR_ENGINE = os.getenv("PAPERLESS_REMOTE_OCR_ENGINE")
REMOTE_OCR_API_KEY = os.getenv("PAPERLESS_REMOTE_OCR_API_KEY")
REMOTE_OCR_ENDPOINT = os.getenv("PAPERLESS_REMOTE_OCR_ENDPOINT")
REMOTE_OCR_MODE = os.getenv("PAPERLESS_REMOTE_OCR_MODE", "always")
################################################################################
# AI Settings #
@@ -21,7 +21,6 @@ from unittest.mock import Mock
import pytest
from documents.parsers import ParseError
from paperless.models import ApplicationConfiguration
from paperless.parsers import ParserContext
from paperless.parsers import ParserProtocol
from paperless.parsers.remote import RemoteDocumentParser
@@ -34,10 +33,6 @@ if TYPE_CHECKING:
from pytest_mock import MockerFixture
# Remote ocr config from ApplicationConfiguration needs DB access
pytestmark = pytest.mark.django_db
# ---------------------------------------------------------------------------
# Module-local fixtures
# ---------------------------------------------------------------------------
@@ -232,18 +227,6 @@ class TestRemoteParserScore:
score = RemoteDocumentParser.score("application/pdf", "doc.pdf")
assert score is not None and score > 10
@pytest.mark.usefixtures("no_engine_settings")
def test_score_uses_app_config_when_env_unset(self) -> None:
"""The app config alone is enough to activate the parser."""
config = ApplicationConfiguration.objects.first()
assert config is not None
config.remote_ocr_engine = "azureai"
config.remote_ocr_api_key = "app-config-key"
config.remote_ocr_endpoint = "https://config.cognitiveservices.azure.com"
config.save()
assert RemoteDocumentParser.score("application/pdf", "doc.pdf") == 20
# ---------------------------------------------------------------------------
# Properties
@@ -1277,8 +1277,6 @@ class TestParserFileTypes:
# ---------------------------------------------------------------------------
# Remote ocr config from ApplicationConfiguration needs DB access
@pytest.mark.django_db
class TestRasterisedDocumentParserRegistry:
def test_registered_in_defaults(self) -> None:
from paperless.parsers.registry import ParserRegistry
+18 -10
View File
@@ -15,7 +15,7 @@ from paperless.checks import audit_log_check
from paperless.checks import binaries_check
from paperless.checks import check_default_language_available
from paperless.checks import check_deprecated_db_settings
from paperless.checks import check_remote_ocr_mode
from paperless.checks import check_remote_parser_configured
from paperless.checks import check_v3_minimum_upgrade_version
from paperless.checks import debug_mode_check
from paperless.checks import paths_check
@@ -631,21 +631,29 @@ class TestV3MinimumUpgradeVersionCheck:
assert check_v3_minimum_upgrade_version(None) == []
class TestRemoteOCRModeCheck:
def test_valid_mode(self, settings: SettingsWrapper) -> None:
settings.REMOTE_OCR_MODE = "workflow_only"
msgs = check_remote_ocr_mode(None)
class TestRemoteParserChecks:
def test_no_engine(self, settings: SettingsWrapper) -> None:
settings.REMOTE_OCR_ENGINE = None
msgs = check_remote_parser_configured(None)
assert len(msgs) == 0
def test_invalid_mode(self, settings: SettingsWrapper) -> None:
settings.REMOTE_OCR_MODE = "sometimes"
def test_azure_no_endpoint(self, settings: SettingsWrapper) -> None:
msgs = check_remote_ocr_mode(None)
settings.REMOTE_OCR_ENGINE = "azureai"
settings.REMOTE_OCR_API_KEY = "somekey"
settings.REMOTE_OCR_ENDPOINT = None
msgs = check_remote_parser_configured(None)
assert len(msgs) == 1
assert "PAPERLESS_REMOTE_OCR_MODE is set to 'sometimes'" in msgs[0].msg
msg = msgs[0]
assert (
"Azure AI remote parser requires endpoint and API key to be configured."
in msg.msg
)
class TestTesseractChecks:
-118
View File
@@ -468,124 +468,6 @@ class TestParserRegistryGetParserForFile:
assert result is AcceptingBuiltin
class TestParserRegistryRemoteParsers:
"""Verify the allow_remote filter in ParserRegistry.get_parser_for_file()."""
@staticmethod
def _remote_parser_cls() -> type:
class RemoteParser:
name = "remote"
version = "1.0"
author = "A"
url = "https://example.com/remote"
uses_remote_service = True
@classmethod
def supported_mime_types(cls):
return {"text/plain": ".txt"}
@classmethod
def score(cls, mime_type, filename, path=None):
return 20
return RemoteParser
def test_remote_parser_wins_when_remote_allowed(
self,
dummy_parser_cls: type,
) -> None:
"""
GIVEN: A remote parser scoring 20 and a local parser scoring 10.
WHEN: get_parser_for_file() is called with allow_remote=True.
THEN: The remote parser is returned.
"""
remote_parser_cls = self._remote_parser_cls()
registry = ParserRegistry()
registry.register_builtin(dummy_parser_cls)
registry.register_builtin(remote_parser_cls)
result = registry.get_parser_for_file(
"text/plain",
"readme.txt",
allow_remote=True,
)
assert result is remote_parser_cls
def test_remote_parser_skipped_when_remote_not_allowed(
self,
dummy_parser_cls: type,
) -> None:
"""
GIVEN: A remote parser scoring 20 and a local parser scoring 10.
WHEN: get_parser_for_file() is called with allow_remote=False.
THEN: The local parser is returned despite its lower score.
"""
registry = ParserRegistry()
registry.register_builtin(dummy_parser_cls)
registry.register_builtin(self._remote_parser_cls())
result = registry.get_parser_for_file(
"text/plain",
"readme.txt",
allow_remote=False,
)
assert result is dummy_parser_cls
def test_no_parser_when_only_remote_available_and_not_allowed(self) -> None:
"""
GIVEN: A registry whose only candidate declares uses_remote_service.
WHEN: get_parser_for_file() is called with allow_remote=False.
THEN: None is returned the remote parser is never used as a
fallback when remote processing was not requested.
"""
registry = ParserRegistry()
registry.register_builtin(self._remote_parser_cls())
result = registry.get_parser_for_file(
"text/plain",
"readme.txt",
allow_remote=False,
)
assert result is None
def test_parser_without_attribute_treated_as_local(
self,
dummy_parser_cls: type,
) -> None:
"""
GIVEN: A third-party parser predating uses_remote_service, so it does
not declare the attribute at all.
WHEN: get_parser_for_file() is called with allow_remote=False.
THEN: It is still considered, i.e. treated as fully local, rather
than raising AttributeError.
"""
assert not hasattr(dummy_parser_cls, "uses_remote_service")
registry = ParserRegistry()
registry.register_builtin(dummy_parser_cls)
result = registry.get_parser_for_file(
"text/plain",
"readme.txt",
allow_remote=False,
)
assert result is dummy_parser_cls
def test_remote_allowed_by_default(self) -> None:
"""
GIVEN: A registry containing only a remote parser.
WHEN: get_parser_for_file() is called without allow_remote.
THEN: The remote parser is returned callers that do not opt in to
the filter keep the previous behaviour.
"""
remote_parser_cls = self._remote_parser_cls()
registry = ParserRegistry()
registry.register_builtin(remote_parser_cls)
result = registry.get_parser_for_file("text/plain", "readme.txt")
assert result is remote_parser_cls
class TestDiscover:
"""Verify entrypoint discovery in ParserRegistry.discover()."""
@@ -1,113 +0,0 @@
"""Tests for RemoteOCRConfig precedence between app config and Django settings."""
from __future__ import annotations
from typing import TYPE_CHECKING
import pytest
from django.test import override_settings
from paperless.config import RemoteOCRConfig
from paperless.models import RemoteOCRMode
if TYPE_CHECKING:
from unittest.mock import MagicMock
@pytest.fixture()
def null_app_config(mocker) -> MagicMock:
"""Mock ApplicationConfiguration with all fields None → falls back to Django settings."""
return mocker.MagicMock(
remote_ocr_engine=None,
remote_ocr_api_key=None,
remote_ocr_endpoint=None,
remote_ocr_mode=None,
)
@pytest.fixture()
def make_remote_ocr_config(mocker):
def _make(app_config, **django_settings_overrides):
mocker.patch(
"paperless.config.BaseConfig._get_config_instance",
return_value=app_config,
)
with override_settings(**django_settings_overrides):
return RemoteOCRConfig()
return _make
class TestRemoteOCRConfig:
def test_falls_back_to_settings(
self,
make_remote_ocr_config,
null_app_config,
) -> None:
cfg = make_remote_ocr_config(
null_app_config,
REMOTE_OCR_ENGINE="azureai",
REMOTE_OCR_API_KEY="env-key",
REMOTE_OCR_ENDPOINT="https://env.cognitiveservices.azure.com",
REMOTE_OCR_MODE=RemoteOCRMode.WORKFLOW_ONLY,
)
assert cfg.remote_ocr_engine == "azureai"
assert cfg.remote_ocr_api_key == "env-key"
assert cfg.remote_ocr_endpoint == "https://env.cognitiveservices.azure.com"
assert cfg.remote_ocr_mode == RemoteOCRMode.WORKFLOW_ONLY
def test_app_config_takes_precedence(
self,
make_remote_ocr_config,
mocker,
) -> None:
app_config = mocker.MagicMock(
remote_ocr_engine="azureai",
remote_ocr_api_key="db-key",
remote_ocr_endpoint="https://db.cognitiveservices.azure.com",
remote_ocr_mode=RemoteOCRMode.WORKFLOW_ONLY,
)
cfg = make_remote_ocr_config(
app_config,
REMOTE_OCR_ENGINE=None,
REMOTE_OCR_API_KEY="env-key",
REMOTE_OCR_ENDPOINT="https://env.cognitiveservices.azure.com",
REMOTE_OCR_MODE=RemoteOCRMode.ALWAYS,
)
assert cfg.remote_ocr_engine == "azureai"
assert cfg.remote_ocr_api_key == "db-key"
assert cfg.remote_ocr_endpoint == "https://db.cognitiveservices.azure.com"
assert cfg.remote_ocr_mode == RemoteOCRMode.WORKFLOW_ONLY
def test_unset_everywhere(
self,
make_remote_ocr_config,
null_app_config,
) -> None:
cfg = make_remote_ocr_config(
null_app_config,
REMOTE_OCR_ENGINE=None,
REMOTE_OCR_API_KEY=None,
REMOTE_OCR_ENDPOINT=None,
)
assert cfg.remote_ocr_engine is None
assert cfg.remote_ocr_api_key is None
assert cfg.remote_ocr_endpoint is None
class TestRemoteOCRByDefault:
def test_always_mode(self, make_remote_ocr_config, null_app_config) -> None:
cfg = make_remote_ocr_config(
null_app_config,
REMOTE_OCR_MODE=RemoteOCRMode.ALWAYS,
)
assert cfg.remote_ocr_by_default is True
def test_workflow_only_mode(self, make_remote_ocr_config, null_app_config) -> None:
cfg = make_remote_ocr_config(
null_app_config,
REMOTE_OCR_MODE=RemoteOCRMode.WORKFLOW_ONLY,
)
assert cfg.remote_ocr_by_default is False
+31 -5
View File
@@ -24,6 +24,7 @@ from paperless_ai.embedding import get_configured_model_name
from paperless_ai.embedding import get_embedding_model
if TYPE_CHECKING:
from django.db.models import QuerySet
from llama_index.core.schema import BaseNode
from paperless_ai.vector_store import PaperlessSqliteVecVectorStore
@@ -252,6 +253,20 @@ def _safe_related_name(document: Document, field: str) -> str | None:
return related.name if related else None
def _document_index_queryset() -> "QuerySet[Document]":
"""Document queryset with every relation build_document_node() /
build_llm_index_text() touches -- correspondent, document_type,
storage_path, tags, notes, custom_fields__field -- pre-loaded, so
indexing one document costs a fixed handful of queries regardless of
its tag or custom field count, instead of one query per related object.
"""
return Document.objects.select_related(
"correspondent",
"document_type",
"storage_path",
).prefetch_related("tags", "notes", "custom_fields__field")
def build_document_node(
document: Document,
*,
@@ -425,11 +440,7 @@ def update_llm_index(
"Skipping LLM index update: migration check deferred; "
"will retry next run."
)
documents = Document.objects.select_related(
"correspondent",
"document_type",
"storage_path",
).prefetch_related("tags", "notes", "custom_fields__field")
documents = _document_index_queryset()
no_documents = not documents.exists()
# Fast exit before touching config: nothing to index and no existing index.
@@ -494,6 +505,21 @@ def update_llm_index(
def llm_index_add_or_update_document(document: Document):
"""Add or atomically replace a document's chunks in the index."""
config = AIConfig()
document_id = document.id
# Re-fetch with the same select_related/prefetch_related shape as the
# bulk path (update_llm_index()) uses: the caller's ``document`` instance
# (e.g. straight off a signal) has none of that loaded, and
# build_document_node()/build_llm_index_text() touch
# correspondent/document_type/storage_path/tags/notes/custom_fields__field
# -- without prefetching, that's one query per related object, including
# one per custom field instance.
document = _document_index_queryset().filter(pk=document_id).first()
if document is None:
logger.info(
"Skipping LLM index update for document %s: it no longer exists.",
document_id,
)
return
new_nodes = build_document_node(
document,
chunk_size=config.llm_embedding_chunk_size,
+68 -8
View File
@@ -735,8 +735,71 @@ class TestLlmIndexAddOrUpdateDocumentEmptyContent:
)
mock_load = mocker.patch("paperless_ai.indexing.load_or_build_index")
doc = MagicMock(spec=Document)
doc.id = 42
doc = DocumentFactory.create()
# Must not raise
indexing.llm_index_add_or_update_document(doc)
mock_load.assert_not_called()
@pytest.mark.django_db
class TestLlmIndexAddOrUpdateDocumentPrefetch:
"""llm_index_add_or_update_document must prefetch the relations
build_document_node()/build_llm_index_text() touch, not re-query per
tag/note/custom field.
"""
def test_query_count_does_not_scale_with_custom_field_count(
self,
temp_llm_index_dir: Path,
mock_embed_model: FakeEmbedding,
) -> None:
"""
GIVEN a document with several custom fields, a note, and a tag
WHEN it is incrementally indexed via llm_index_add_or_update_document
THEN the query count stays flat instead of growing with the number
of custom fields -- a regression here would add one query per
custom field instance (instance.field.name unprefetched), see
build_llm_index_text().
"""
doc = DocumentFactory.create()
Note.objects.create(document=doc, note="a note")
for i in range(5):
field = CustomField.objects.create(
name=f"Field {i}",
data_type=CustomField.FieldDataType.STRING,
)
CustomFieldInstance.objects.create(
document=doc,
field=field,
value_text="value",
)
with CaptureQueriesContext(connection) as ctx:
indexing.llm_index_add_or_update_document(doc)
# Flat regardless of custom field count -- an unprefetched
# custom_fields__field would add one query per instance (5 here) on
# top of this budget.
assert len(ctx.captured_queries) <= 10
def test_skips_write_when_document_no_longer_exists(
self,
temp_llm_index_dir: Path,
mock_embed_model: FakeEmbedding,
mocker: pytest_mock.MockerFixture,
) -> None:
"""
GIVEN a document that has been deleted since the caller looked it up
(e.g. a race between a signal firing and its async task running)
WHEN llm_index_add_or_update_document is called with that stale instance
THEN it skips the write instead of raising Document.DoesNotExist
"""
doc = DocumentFactory.create()
doc_id = doc.pk
Document.objects.filter(pk=doc_id).delete()
mock_load = mocker.patch("paperless_ai.indexing.load_or_build_index")
# Must not raise
indexing.llm_index_add_or_update_document(doc)
@@ -793,8 +856,7 @@ class TestLlmIndexLocking:
return_value=[mock_node],
)
doc = MagicMock(spec=Document)
doc.id = 1
doc = DocumentFactory.create()
indexing.llm_index_add_or_update_document(doc)
mock_store.upsert_document.assert_called_once()
@@ -825,8 +887,7 @@ class TestLlmIndexLocking:
return_value=[mock_node],
)
doc = MagicMock(spec=Document)
doc.id = 1
doc = DocumentFactory.create()
indexing.llm_index_add_or_update_document(doc)
mock_store.upsert_document.assert_not_called()
@@ -863,8 +924,7 @@ class TestLlmIndexLocking:
return_value=[mock_node],
)
doc = MagicMock(spec=Document)
doc.id = 1
doc = DocumentFactory.create()
indexing.llm_index_add_or_update_document(doc)
mock_store.upsert_document.assert_not_called()